This paper presents KnowledgeTree, an architecture for adaptive E-Learning based on distributed reusable intelligent learning activities. The goal of KnowledgeTree is to bridge the gap between the currently popular approach to Web-based education, which is centered on learning management systems vs. the powerful but underused technologies in intelligent tutoring and adaptive hypermedia. This integrative architecture attempts to address both the component-based assembly of adaptive systems and teacher-level reusability.

Personalized support for learners becomes even more important, when e-Learning takes place in open and dynamic learning and information networks. This paper shows how to realize personalized learning support in distributed learning environments based on Semantic Web technologies. Our approach fills the existing gap between current adaptive educational systems with well-established personalization functionality, and open, dynamic learning repository networks. We propose a service-based architecture for establishing personalized e-Learning, where personalization functionality is provided by various web-services. A Personal Learning Assistant integrates personalization services and other supporting services, and provides the personalized access to learning resources in an e-Learning network.

This paper examines the sufficiency of existing eLearning standards for facilitating and supporting the introduction of adaptive techniques in computer-based learning systems. To that end, the main representational and operational requirements of adaptive learning environments are examined and contrasted against current eLearning standards. The motivation behind this preliminary analysis is attainment of: interoperability between adaptive learning systems; reuse of adaptive learning materials; and, the facilitation of adaptively supported, distributed learning activities.

Navigation in information intensive applications to retrieve required information is time consuming task. Without appropriate navigation support the browsing need not lead to required information. One of the navigation support is guiding a user through the information. The guidance has to be adapted according to different requirements and different goals the user can have. A system can adapt the appearence of information and links or links can lead to different alternatives of information based on observed user preferences, goals, level of knowledge. Parametrizing allow us to capture such variability already in the modelling of such applications. Such parametrized models can serve as an input to a generator which will generate appropriate navigation sequence based on the parameters' values. In this paper we discuss a method for generating such adaptive navigation sequences from the UML state diagrams. The method is discussed on a case of adaptive e-course. Latest advances in UML model representation by means of XML based metadata interchange format can be succesfully utilized for adaptive generation of the adaptive navigation sequences and can speed up a prototyping of navigation support in adaptive web-based systems. Adaptive generation means that generator can be parametrized. The parameters' values are set by user intercation with a system. According to the parameters the generator can generate modified navigation support and appearance of information based on the observed user features. The widely accepted standard based means and tools for XML technology are used for implementing a method for transforming UML state diagrams into web site graph and visualisation of that graph.

Robust and scalable user context management is the key enabler for the emerging context- and situation-aware applications, and ontology-based approaches have shown their usefulness for capturing especially context information on a high level of abstraction. But so far the problem has not been approached as a data management problem, which is key to scalability and robustness. The specific challenges lie in the imperfection of high-level context information, its time-dependence and the variability in the dynamics between its different elements.

Abstract—Recommender systems have been researched extensively by the Technology Enhanced Learning (TEL) community during the last decade. By identifying suitable resources from a potentially overwhelming variety of choices, such systems offer a promising approach to facilitate both learning and teaching tasks. As learning is taking place in extremely diverse and rich environments, the incorporation of contextual information about the user in the recommendation process has attracted major interest. Such contextualization is researched as a paradigm for building intelligent systems that can better predict and anticipate the needs of users, and act more efficiently in response to their behavior. In this paper, we try to assess the degree to which current work in TEL recommender systems has achieved this, as well as outline areas in which further work is needed. First, we present a context framework that identifies relevant context dimensions for TEL applications. Then, we present an analysis of existing TEL recommender systems along these dimensions. Finally, based on our survey results, we outline topics on which further research is needed. Index Terms—Adaptive and Intelligent Educational Systems, Personalized E-Learning, System Applications and Experience. F

The challenge of the semantic web is the provision of distributed information with well defined meaning, understandable for different parties. Particularly, applications should be able to provide individually optimized access to information by taking the individual needs and requirements of the users into account. In this paper we propose a framework for personalized e-Learning in the semantic web and show how the semantic web resource description formats can be utilized for automatic generation of hypertext structures from distributed metadata. Ontologies and metadata for three types of resources (domain, user, and observation) are investigated. We investigate a logic-based approach to educational hypermedia using TRIPLE, a rule and query language for the semantic web. keywords: Educational hypermedia, Semantic web, Ontologies, Adaptive hypermedia, Reasoning on the semantic web.

Current research in context-awareness is biased toward low-level context information. High-level context information, however, poses several challenges to context management systems, which can be traced back to the asynchronicity of context acquisition and use and the inherent dynamics and imperfection in that process. This paper presents a three layer model allowing for dealing with the problems of imperfection and aging in a controlled way. It conceives the problem of high-level user context management as an information management problem with specific requirements.

Context-steered learning in enterprises promises both from a learner point of view and from an organizational point of view higher learning efficiency and improved quality control. We present the Learning in Process approach for contextualizing learning processes in a corporate setting. Its nucleus is a matching component compiling personalized learning programs on demand from modular learning objects.

Semantic Web applications offer great potential to student modellers who have traditionally struggled with issues of re-use, portability and tight coupling with le arning applications. In this pape r, we de scribe our use of ontology language s ande - le arning standards to develop a loosely coupled and portable student modelling architecture used in a large-scale, distributed production learning environment.